What is EMD?

Empirical Mode Decomposition for nonlinear and non-stationary signal analysis

Overview

Empirical Mode Decomposition (EMD) is a data-driven method for decomposing complex signals into simpler oscillatory components called Intrinsic Mode Functions (IMFs). Unlike Fourier analysis, EMD makes no assumptions about linearity or stationarity.

Presentation Outline

  1. 1 What is EMD (this page)
  2. 2 Local Median Approach
  3. 3 Sifting Process & Results

Application Domain: Cryptocurrency Returns Analysis

Empirical Mode Decomposition

Core Idea

EMD decomposes a signal into nonlinear and non-stationary components that are extracted adaptively from the data itself. The result is a collection of Intrinsic Mode Functions (IMFs) plus a residual trend.

Signal Decomposition:

\[ X(t) = \sum_{k=1}^{K} \text{IMF}_k(t) + r(t) \]

where \(\text{IMF}_k\) are the intrinsic mode functions and \(r(t)\) is the residual trend.

Key Features

Adaptive Decomposition

The decomposition is entirely data-dependent, not relying on predetermined basis functions.

No Linearity Assumption

Works for nonlinear systems where Fourier methods fail.

Non-stationary Signals

Handles time-varying frequency and amplitude naturally.

Time-Frequency Analysis

Each IMF captures oscillations at a characteristic time scale.

Envelope-Based Sifting

Traditional EMD uses envelope detection to identify the local mean:

Upper Lower Mean
Signal
Upper Envelope
Lower Envelope
Local Mean

The local mean is computed as the average of upper and lower envelopes connecting local maxima and minima.

AM-FM Signal Model

For testing and validation, we use an amplitude-modulated, frequency-modulated (AM-FM) signal that exhibits both time-varying amplitude and instantaneous frequency.

Why AM-FM Signals?

AM-FM signals are ideal test cases because they are non-stationary by construction, have known ground truth for validation, and appear naturally in many applications (speech, radar, biomedical signals, financial data).

Mathematical Specification

Amplitude Modulation:

\[ A(x) = 1 + 0.5 \sin(4\pi x) \]

The amplitude varies between 0.5 and 1.5 with period 0.5.

Phase Function:

\[ \phi(x) = 2\pi (6x + 12x^2) \]

Quadratic phase creates a chirp (increasing frequency).

Instantaneous Frequency:

\[ f(x) = \frac{1}{2\pi}\frac{d\phi}{dx} = 6 + 24x \]

Frequency increases linearly from 6 Hz at x=0 to 30 Hz at x=1.

Clean Signal:

\[ y_{\text{clean}}(x) = A(x) \sin(\phi(x)) = [1 + 0.5\sin(4\pi x)] \sin(2\pi(6x + 12x^2)) \]

Noisy Signal:

\[ y(x) = y_{\text{clean}}(x) + \sigma \varepsilon(x), \quad \varepsilon \sim \mathcal{N}(0,1) \]

We typically use \(\sigma = 0.2\) for examples.

Signal Characteristics

Property Value Description
Amplitude Range [0.5, 1.5] Modulated by low-frequency sinusoid
Frequency Range [6, 30] Hz Linear chirp (increasing frequency)
Noise Level \(\sigma = 0.2\) Moderate Gaussian noise
Domain \(x \in [0, 1]\) Normalized time interval

Three Decomposition Approaches

We compare three methods for computing the local trend in the sifting process:

1. Local Median (Recommended)

Kernel-weighted median using Epanechnikov kernel. Robust to outliers with 50% breakdown point.

Learn more

2. Median Approach

Running median with efficient heap-based computation (Hardle & Steiger 1995).

3. Average Approach

Standard Nadaraya-Watson kernel regression. Not robust to outliers.

The Local Median approach combines the adaptivity of kernel smoothing with the robustness of the median, making it ideal for financial time series that often contain extreme values.

Next Steps